Sensorimotor Exploration/Exploitation with Coordinating Local Predictions

Jean-Charles Quinton (1, 2)

1 CORTEX - Neuromimetic intelligence
2 IRIT - Institut de recherche en informatique de Toulouse

This contribution aims to show how exploration and exploitation might be tightly intertwined when modeling sensorimotor behaviors with coordinated predictive local representations. In such a framework, learning equals to creating and selecting anticipations to adapt to the dynamics of the agent and its environment. Motor actions are undertaken based on the expected outcome of the anticipations, and anticipations reinforced when successfully matching the dynamics. Reaching goals is thus equivalent to navigating through the sensorimotor space by forming and following chains of coordinated predictions. Although the agent may constantly only try to exploit its knowledge, the presence of multiple dynamic goals, the lack of correct anticipations, interactional noise or external constraint will lead to further exploration and the generation of new task-independent representations.

Domaines: Informatique

Jean-Charles Quinton. Sensorimotor Exploration/Exploitation with Coordinating Local Predictions. 4th International Conference on Cognitive Systems (CogSys 2010), Jan 2010, Zürich, Switzerland. ⟨inria-00536870⟩